Bratin Roy, Vice President, Industry Services, TÜV SÜD South Asia, explains how predictive maintenance at power plants, can be a solution to reduce unplanned generation and efficiency loss.
Ageing power plants possess threat of very high maintenance costs and unscheduled breakdowns, whereas capacity addition to new plants require high investment. In both these cases, operation of any conventional power plants requires upgrades to ease out the operational and maintenance challenges.
The plants operators face the problem of having low maintenance techniques which expose them to unscheduled breakdowns, generation loss, high cost in emergency and high safety risks even after best techniques available today. It is thus important to explore the possibility of new maintenance technique which is based on prediction of plant status, maintenance needs as well as performance.
After years of relying on preventive maintenance, the power generation industry is moving into a new maintenance territory. Powerful predictive maintenance technologies and services are changing the face and the future of the industry, and technology is leading the charge from remote monitoring and diagnostics tools to Big Data analytics and management.
As the foundation of such a solution is prediction, it is popularly known as ‘Predictive maintenance’ solutions in power plants. This predictive maintenance technique will be fully based on sensor inputs in real time with support technologies like cloud, modelling and real time simulations to provide features like plant status, maintenance predictions, operating risk, performance controls along with remote support, organised history on plant status, performance and condition.
The ability to foresee issues until an optimal planned maintenance outage date can be selected, is the core of predictive maintenance.
Problems & features
There are many problems and uncertainties faced by an operator regarding breaking down of a power plant. Some of them are no warning on breakdown; no warning on life; high cost on sudden breakdown, i.e. unbudgeted cost; time constrains, including expert availability issues; non-availability of organised data; and degradation of assets; and non-availability of a holistic solution, as the existing solutions are more component based.
Meanwhile, from our experiences of working with various power generators and utilities, the most desirable features list which a customers want to have are remote support; and early working system; an alert system on degradation; holistic solution to look after complete plant system; risk-based predictive maintenance solution; real time assessment; and on demand history.
Approach for implementation
Preventative maintenance largely is a calendar-based approach, that calls for equipment to be serviced or replaced at predetermined intervals. This could include replacing a circuit breaker or motors or conveyor belt based on a specified time interval or number of operations.
However, online predictive maintenance is part of a comprehensive strategy that involves using software technology for real-time monitoring of equipment’s health and comparing its current operational state to a model that defines normal or ideal operating conditions. Predictive analytics software uses advanced algorithms to detect subtle operational variances for each piece of equipment, which often warn of impending problems that might have gone unnoticed otherwise. Utilities can create automated alarm notifications and use the software to diagnose the source of equipment and system anomalies, in addition to prioritising issues based on severity.
Predictive maintenance is a data-intensive strategy that involves performing a failure mode, effects and criticality analysis (FMECA); fault tree analysis for assets and then implementing maintenance strategies based on the results. Using this strategy, equipment maintenance is altered and prioritised by its importance to the overall health of the plant, grid or facility.
A predictive maintenance strategy is most beneficial with the implementation of proper online condition monitoring and analytics software. Typically, predictive analytics software analyses information from an enterprise historian, ensuring all historical and real-time sensor data is included in the analysis and model building.
Key steps for implementation of a successful predictive maintenance plan are: a proper condition assessment and baseline study; selection, installation and integration of sensors and monitoring system; implementation of an effective system of big data handling and analytics; development and implementation of plant specific risk and predictive model; integration with existing IT infrastructure and finalisation of delivery output.
After making significant investments in modern control, monitoring and smart devices, predictive monitoring techniques allow utilities to extend that investment by using and analysing collected data to make informed maintenance decisions.
By using advanced predictive analytics and diagnostic technology as part of a comprehensive maintenance program, utilities can monitor critical assets to predict.
From our decade long experience on working extensively in this sector, it can be safely presumed that extending traditional maintenance by using predictive techniques enables better plant management. It also increases reliability, safety standards and the residual life of machine components, and reduces unnecessary repairs.
There can be a major reduction in maintenance costs compared with periodical maintenance or fixed-interval maintenance. Using advanced predictive analytics and diagnostic technology as part of a comprehensive predictive maintenance program, utilities can monitor critical assets to predict, diagnose and prioritise potential equipment problems continuously and in real time.
Based on the real-time data and usefulness of the asset, the operators know what they will need, and the parts can be ordered ahead of time, which can also help reduce the outage timing. If a utility is forecasting a 3-week outage, with proper planning and analytics, an outage can be reduced by up to a week, saving the power plant provider’s time and money.
To make this system successful, one needs to engage a highly qualified, experienced and multi-disciplined team. The combination of data analysis, technical experience and reasonable hypotheses forms a winning strategy for failure prediction.
I wish to start pvc / pp electric wire unit in Delhi. What kind of information I can get if I subscribe for your magazine
Pls invite me all auction in gujarat
we are doing business developing for solar power ,thermal power , customer supporting and we have 45 mw splar power on hand needs investors.....
pls call +910842559230